INDEX

Explanations

technical terms and concepts related to engineering and products

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ?>:</

-0.16

Ø±Ø²

-0.15

imony

-0.15

.toDouble

-0.15

ivor

-0.15

/Area

-0.15

CCCCCC

-0.14

erse

-0.14

sole

-0.14

(åľŁ

-0.14

POSITIVE LOGITS

uran

0.17

èĥ

0.14

ettel

0.14

ìľµ

0.14

 subst

0.14

ãĥ«ãĥĪ

0.14

ajar

0.14

hdl

0.14

supply

0.13

Lex

0.13

Activations Density 0.023%

technical terms and concepts related to engineering and products

No Comments

No Known Activations